% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Chen:1030925,
author = {Chen, Pansheng and An, Lijun and Wulan, Naren and Zhang,
Chen and Zhang, Shaoshi and Ooi, Leon Qi Rong and Kong, Ru
and Chen, Jianzhong and Wu, Jianxiao and Chopra, Sidhant and
Bzdok, Danilo and Eickhoff, Simon B. and Holmes, Avram J.
and Yeo, B. T. Thomas},
title = {{M}ultilayer meta-matching: {T}ranslating phenotypic
prediction models from multiple datasets to small data},
journal = {Imaging neuroscience},
volume = {2},
issn = {2837-6056},
address = {Cambridge, MA},
publisher = {MIT Press},
reportid = {FZJ-2024-05518},
pages = {1 - 22},
year = {2024},
abstract = {Resting-state functional connectivity (RSFC) is widely used
to predict phenotypic traits in individuals. Large sample
sizes can significantly improve prediction accuracies.
However, for studies of certain clinical populations or
focused neuroscience inquiries, small-scale datasets often
remain a necessity. We have previously proposed a
“meta-matching” approach to translate prediction models
from large datasets to predict new phenotypes in small
datasets. We demonstrated a large improvement over classical
kernel ridge regression (KRR) when translating models from a
single source dataset (UK Biobank) to the Human Connectome
Project Young Adults (HCP-YA) dataset. In the current study,
we propose two meta-matching variants (“meta-matching with
dataset stacking” and “multilayer meta-matching”) to
translate models from multiple source datasets across
disparate sample sizes to predict new phenotypes in small
target datasets. We evaluate both approaches by translating
models trained from five source datasets (with sample sizes
ranging from 862 participants to 36,834 participants) to
predict phenotypes in the HCP-YA and HCP-Aging datasets. We
find that multilayer meta-matching modestly outperforms
meta-matching with dataset stacking. Both meta-matching
variants perform better than the original “meta-matching
with stacking” approach trained only on the UK Biobank.
All meta-matching variants outperform classical KRR and
transfer learning by a large margin. In fact, KRR is better
than classical transfer learning when less than 50
participants are available for finetuning, suggesting the
difficulty of classical transfer learning in the very small
sample regime. The multilayer meta-matching model is
publicly available at
$https://github.com/ThomasYeoLab/Meta_matching_models/tree/main/rs-fMRI/v2.0.$},
cin = {INM-7},
ddc = {050},
cid = {I:(DE-Juel1)INM-7-20090406},
pnm = {5254 - Neuroscientific Data Analytics and AI (POF4-525) /
5252 - Brain Dysfunction and Plasticity (POF4-525)},
pid = {G:(DE-HGF)POF4-5254 / G:(DE-HGF)POF4-5252},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001525523700001},
doi = {10.1162/imag_a_00233},
url = {https://juser.fz-juelich.de/record/1030925},
}